Parallel Data Mining for Association Rules on Shared-Memory Systems

被引：73

作者：

S. Parthasarathy

M. J. Zaki

M. Ogihara

W. Li

机构：

[1] Department of Computer and Information Sciences,

[2] Ohio State University,undefined

[3] Columbus,undefined

[4] OH,undefined

[5] USA,undefined

[6] Department of Computer Science,undefined

[7] Rensselaer Polytechnic Institute,undefined

[8] Troy,undefined

[9] NY,undefined

[10] USA,undefined

[11] Department of Computer Science,undefined

[12] University of Rochester,undefined

[13] Rochester,undefined

[14] NY,undefined

[15] USA,undefined

[16] Intel Corporation,undefined

[17] Santa Clara,undefined

[18] CA,undefined

[19] USA,undefined

来源：

Knowledge and Information Systems | 2001年 / 3卷 / 1期

关键词：

Keywords: Association rules; Improving locality; Memory placement; Parallel data mining; Reducing false sharing;

D O I：

10.1007/PL00011656

中图分类号：

学科分类号：

摘要：

In this paper we present a new parallel algorithm for data mining of association rules on shared-memory multiprocessors. We study the degree of parallelism, synchronization, and data locality issues, and present optimizations for fast frequency computation. Experiments show that a significant improvement of performance is achieved using our proposed optimizations. We also achieved good speed-up for the parallel algorithm.

引用

页码：1 / 29

页数：28